Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2718 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.6205. Min Act: -0.1700
Data Index: 8134601 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.5892. Min Act: -0.1700
Data Index: 5573671 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.5892. Min Act: -0.1700
Data Index: 5899861 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.4017. Min Act: -0.1700
Data Index: 2671618 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.3705. Min Act: -0.1700
Data Index: 2438608 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.3392. Min Act: -0.1700
Data Index: 8634043 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.2455. Min Act: -0.1700
Data Index: 2245703 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.2142. Min Act: -0.1700
Data Index: 1252958 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.2142. Min Act: -0.1700
Data Index: 935053 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.1830. Min Act: -0.1700
Data Index: 1078746 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.1517. Min Act: -0.1700
Data Index: 958920 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.1830. Min Act: -0.1700
Data Index: 8557602 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.1517. Min Act: -0.1700
Data Index: 286820 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.1517. Min Act: -0.1700
Data Index: 4330403 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.1517. Min Act: -0.1700
Data Index: 6099548 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.0892. Min Act: -0.1700
Data Index: 3319371 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.0892. Min Act: -0.1700
Data Index: 4055608 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.0892. Min Act: -0.1700
Data Index: 3560306 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.0580. Min Act: -0.1700
Data Index: 6906336 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6205. Min Range: -5.6205
Max Act: 5.0580. Min Act: -0.1700
Data Index: 3537002 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19